研究库 论文知识库

内容库 / 论文

arXiv:2610.08674 · RAG 检索增强

EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding

EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding

类型：arxiv
标识：2610.08674
链接：http://arxiv.org/abs/2610.08674v1
主分类：rag
形态：method
TLDR：Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although retrieval-augmented approaches have been introduced to provide additional context, most of them operate at the frame or snippet level, which limits their ability to model how events evolve over time and relate to each other. In this paper, we propose Event Chain Retrieval-Augmented Generation (EC-RAG), a training-free framework that organizes video content into an ex
副分类：multimodal
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-10-07-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记 LoomVideo · Unifying Multimodal Inputs into Video Generation and Editing · 批判性精读

笔记 Thinking with Video 短审稿 · 2026-06-17

仓库 EvolvingLMMs-Lab/lmms-eval

笔记 LingBot-Video MoE 视角精读 · v2 重写覆盖原 7-13 22:51 短补稿

笔记 Video-DeepResearch (Video-DR) 短审稿 + 与 LongVideoAgent / Vision-DR lineage 衔接

笔记 MAVIN · 多镜头音视频联合生成 · 批判性精读

arXiv

2610.08674

TLDR

Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although retrieval-augmented approaches have been introduced to provide additional context, most of them operate at the frame or snippet level, which limits their ability to model how events evolve over time and relate to each other. In this paper, we propose Event Chain Retrieval-Augmented Generation (EC-RAG), a training-free framework that organizes video content into an ex

arXiv ↗ 中文全文